cimol commited on
Commit
3db85e1
·
verified ·
1 Parent(s): d9ce4cb

Training in progress, step 150, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9378d75810abf450abcc091bbe23663f53b94976717b4fa71ed929c9ba62a8ca
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:407d4c0fb976eafd0d8bd30ed9bb1f6d0c5e3723cc42b4807b644074697d8db6
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a1712a8c9dd8ab372e655cdf3753005620287f226c490cfd4bcbf1da185e360
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92618a59c2b1647ee30ad93c6849c151a71a5fe658d31af52bdb065b6f519f40
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf3928560a0fac89e8dc1f8d64c9624302321953123449d57a1d66545f916a5e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce5aaeff37c40ce6cd28956554515b414e4709438e0955a8333d9abc788000ce
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d94dee72c7d02de6c69d9fa4cc2d9dd3225f09ac52c6adcb59ec7bae1df8f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b26348e70deb5f7d6cee52f5eb084c0e6829440001a3c6d0128b93cd074af8c2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1414027214050293,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.19038553069966682,
5
  "eval_steps": 50,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -731,6 +731,364 @@
731
  "eval_samples_per_second": 13.513,
732
  "eval_steps_per_second": 3.39,
733
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
734
  }
735
  ],
736
  "logging_steps": 1,
@@ -759,7 +1117,7 @@
759
  "attributes": {}
760
  }
761
  },
762
- "total_flos": 1.430999619600384e+17,
763
  "train_batch_size": 8,
764
  "trial_name": null,
765
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0172055959701538,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
+ "epoch": 0.28557829604950025,
5
  "eval_steps": 50,
6
+ "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
731
  "eval_samples_per_second": 13.513,
732
  "eval_steps_per_second": 3.39,
733
  "step": 100
734
+ },
735
+ {
736
+ "epoch": 0.19228938600666348,
737
+ "grad_norm": 8.70529556274414,
738
+ "learning_rate": 3.7313170451399475e-05,
739
+ "loss": 5.0098,
740
+ "step": 101
741
+ },
742
+ {
743
+ "epoch": 0.19419324131366017,
744
+ "grad_norm": 8.006318092346191,
745
+ "learning_rate": 3.673543141356278e-05,
746
+ "loss": 5.0347,
747
+ "step": 102
748
+ },
749
+ {
750
+ "epoch": 0.19609709662065683,
751
+ "grad_norm": 7.4283013343811035,
752
+ "learning_rate": 3.6157217926105783e-05,
753
+ "loss": 4.8268,
754
+ "step": 103
755
+ },
756
+ {
757
+ "epoch": 0.1980009519276535,
758
+ "grad_norm": 6.7939605712890625,
759
+ "learning_rate": 3.557868806682255e-05,
760
+ "loss": 4.7183,
761
+ "step": 104
762
+ },
763
+ {
764
+ "epoch": 0.19990480723465018,
765
+ "grad_norm": 6.694666862487793,
766
+ "learning_rate": 3.5e-05,
767
+ "loss": 4.6545,
768
+ "step": 105
769
+ },
770
+ {
771
+ "epoch": 0.20180866254164684,
772
+ "grad_norm": 6.7515692710876465,
773
+ "learning_rate": 3.442131193317745e-05,
774
+ "loss": 4.5719,
775
+ "step": 106
776
+ },
777
+ {
778
+ "epoch": 0.2037125178486435,
779
+ "grad_norm": 6.9047932624816895,
780
+ "learning_rate": 3.384278207389421e-05,
781
+ "loss": 4.3211,
782
+ "step": 107
783
+ },
784
+ {
785
+ "epoch": 0.20561637315564016,
786
+ "grad_norm": 8.433969497680664,
787
+ "learning_rate": 3.3264568586437216e-05,
788
+ "loss": 4.414,
789
+ "step": 108
790
+ },
791
+ {
792
+ "epoch": 0.20752022846263685,
793
+ "grad_norm": 6.5694050788879395,
794
+ "learning_rate": 3.268682954860052e-05,
795
+ "loss": 4.2368,
796
+ "step": 109
797
+ },
798
+ {
799
+ "epoch": 0.2094240837696335,
800
+ "grad_norm": 7.584961891174316,
801
+ "learning_rate": 3.210972290846837e-05,
802
+ "loss": 4.6716,
803
+ "step": 110
804
+ },
805
+ {
806
+ "epoch": 0.21132793907663017,
807
+ "grad_norm": 6.995484828948975,
808
+ "learning_rate": 3.15334064412338e-05,
809
+ "loss": 4.3203,
810
+ "step": 111
811
+ },
812
+ {
813
+ "epoch": 0.21323179438362685,
814
+ "grad_norm": 7.1296467781066895,
815
+ "learning_rate": 3.0958037706064485e-05,
816
+ "loss": 4.5241,
817
+ "step": 112
818
+ },
819
+ {
820
+ "epoch": 0.21513564969062351,
821
+ "grad_norm": 7.044524669647217,
822
+ "learning_rate": 3.038377400302758e-05,
823
+ "loss": 4.4863,
824
+ "step": 113
825
+ },
826
+ {
827
+ "epoch": 0.21703950499762018,
828
+ "grad_norm": 7.043889045715332,
829
+ "learning_rate": 2.9810772330085524e-05,
830
+ "loss": 4.4081,
831
+ "step": 114
832
+ },
833
+ {
834
+ "epoch": 0.21894336030461684,
835
+ "grad_norm": 8.038551330566406,
836
+ "learning_rate": 2.9239189340174306e-05,
837
+ "loss": 4.5455,
838
+ "step": 115
839
+ },
840
+ {
841
+ "epoch": 0.22084721561161352,
842
+ "grad_norm": 7.743556499481201,
843
+ "learning_rate": 2.8669181298376163e-05,
844
+ "loss": 4.3879,
845
+ "step": 116
846
+ },
847
+ {
848
+ "epoch": 0.22275107091861018,
849
+ "grad_norm": 7.689728260040283,
850
+ "learning_rate": 2.8100904039198193e-05,
851
+ "loss": 4.3637,
852
+ "step": 117
853
+ },
854
+ {
855
+ "epoch": 0.22465492622560684,
856
+ "grad_norm": 7.642689228057861,
857
+ "learning_rate": 2.7534512923968863e-05,
858
+ "loss": 4.5594,
859
+ "step": 118
860
+ },
861
+ {
862
+ "epoch": 0.22655878153260353,
863
+ "grad_norm": 8.036393165588379,
864
+ "learning_rate": 2.6970162798363695e-05,
865
+ "loss": 4.2413,
866
+ "step": 119
867
+ },
868
+ {
869
+ "epoch": 0.2284626368396002,
870
+ "grad_norm": 7.012694358825684,
871
+ "learning_rate": 2.640800795007203e-05,
872
+ "loss": 4.2993,
873
+ "step": 120
874
+ },
875
+ {
876
+ "epoch": 0.23036649214659685,
877
+ "grad_norm": 7.756348133087158,
878
+ "learning_rate": 2.5848202066616305e-05,
879
+ "loss": 4.1293,
880
+ "step": 121
881
+ },
882
+ {
883
+ "epoch": 0.23227034745359354,
884
+ "grad_norm": 7.184790134429932,
885
+ "learning_rate": 2.5290898193335446e-05,
886
+ "loss": 4.0667,
887
+ "step": 122
888
+ },
889
+ {
890
+ "epoch": 0.2341742027605902,
891
+ "grad_norm": 6.861097812652588,
892
+ "learning_rate": 2.4736248691543736e-05,
893
+ "loss": 3.9088,
894
+ "step": 123
895
+ },
896
+ {
897
+ "epoch": 0.23607805806758686,
898
+ "grad_norm": 7.792126655578613,
899
+ "learning_rate": 2.4184405196876842e-05,
900
+ "loss": 4.0982,
901
+ "step": 124
902
+ },
903
+ {
904
+ "epoch": 0.23798191337458352,
905
+ "grad_norm": 8.279322624206543,
906
+ "learning_rate": 2.363551857783608e-05,
907
+ "loss": 4.273,
908
+ "step": 125
909
+ },
910
+ {
911
+ "epoch": 0.2398857686815802,
912
+ "grad_norm": 7.2576494216918945,
913
+ "learning_rate": 2.308973889454249e-05,
914
+ "loss": 4.133,
915
+ "step": 126
916
+ },
917
+ {
918
+ "epoch": 0.24178962398857687,
919
+ "grad_norm": 8.2999906539917,
920
+ "learning_rate": 2.2547215357711918e-05,
921
+ "loss": 4.0224,
922
+ "step": 127
923
+ },
924
+ {
925
+ "epoch": 0.24369347929557353,
926
+ "grad_norm": 8.445121765136719,
927
+ "learning_rate": 2.2008096287862266e-05,
928
+ "loss": 4.2589,
929
+ "step": 128
930
+ },
931
+ {
932
+ "epoch": 0.24559733460257022,
933
+ "grad_norm": 7.673584938049316,
934
+ "learning_rate": 2.1472529074764177e-05,
935
+ "loss": 4.3057,
936
+ "step": 129
937
+ },
938
+ {
939
+ "epoch": 0.24750118990956688,
940
+ "grad_norm": 7.786920547485352,
941
+ "learning_rate": 2.0940660137146074e-05,
942
+ "loss": 4.2528,
943
+ "step": 130
944
+ },
945
+ {
946
+ "epoch": 0.24940504521656354,
947
+ "grad_norm": 7.61902379989624,
948
+ "learning_rate": 2.041263488266484e-05,
949
+ "loss": 3.7492,
950
+ "step": 131
951
+ },
952
+ {
953
+ "epoch": 0.2513089005235602,
954
+ "grad_norm": 7.465391159057617,
955
+ "learning_rate": 1.988859766815275e-05,
956
+ "loss": 3.981,
957
+ "step": 132
958
+ },
959
+ {
960
+ "epoch": 0.25321275583055686,
961
+ "grad_norm": 7.733811855316162,
962
+ "learning_rate": 1.9368691760151773e-05,
963
+ "loss": 4.1569,
964
+ "step": 133
965
+ },
966
+ {
967
+ "epoch": 0.2551166111375536,
968
+ "grad_norm": 7.370545387268066,
969
+ "learning_rate": 1.885305929574593e-05,
970
+ "loss": 3.874,
971
+ "step": 134
972
+ },
973
+ {
974
+ "epoch": 0.25702046644455023,
975
+ "grad_norm": 8.920854568481445,
976
+ "learning_rate": 1.8341841243702424e-05,
977
+ "loss": 4.3121,
978
+ "step": 135
979
+ },
980
+ {
981
+ "epoch": 0.2589243217515469,
982
+ "grad_norm": 9.357240676879883,
983
+ "learning_rate": 1.7835177365932225e-05,
984
+ "loss": 4.524,
985
+ "step": 136
986
+ },
987
+ {
988
+ "epoch": 0.26082817705854355,
989
+ "grad_norm": 8.812352180480957,
990
+ "learning_rate": 1.7333206179280478e-05,
991
+ "loss": 3.9994,
992
+ "step": 137
993
+ },
994
+ {
995
+ "epoch": 0.2627320323655402,
996
+ "grad_norm": 8.463519096374512,
997
+ "learning_rate": 1.6836064917657478e-05,
998
+ "loss": 4.0683,
999
+ "step": 138
1000
+ },
1001
+ {
1002
+ "epoch": 0.2646358876725369,
1003
+ "grad_norm": 7.832219123840332,
1004
+ "learning_rate": 1.6343889494520224e-05,
1005
+ "loss": 3.9524,
1006
+ "step": 139
1007
+ },
1008
+ {
1009
+ "epoch": 0.26653974297953353,
1010
+ "grad_norm": 8.509306907653809,
1011
+ "learning_rate": 1.5856814465715064e-05,
1012
+ "loss": 3.9898,
1013
+ "step": 140
1014
+ },
1015
+ {
1016
+ "epoch": 0.26844359828653025,
1017
+ "grad_norm": 8.911566734313965,
1018
+ "learning_rate": 1.5374972992691458e-05,
1019
+ "loss": 3.9925,
1020
+ "step": 141
1021
+ },
1022
+ {
1023
+ "epoch": 0.2703474535935269,
1024
+ "grad_norm": 9.420488357543945,
1025
+ "learning_rate": 1.4898496806096974e-05,
1026
+ "loss": 4.1377,
1027
+ "step": 142
1028
+ },
1029
+ {
1030
+ "epoch": 0.27225130890052357,
1031
+ "grad_norm": 8.05871868133545,
1032
+ "learning_rate": 1.4427516169763444e-05,
1033
+ "loss": 3.8602,
1034
+ "step": 143
1035
+ },
1036
+ {
1037
+ "epoch": 0.27415516420752023,
1038
+ "grad_norm": 8.699991226196289,
1039
+ "learning_rate": 1.396215984509412e-05,
1040
+ "loss": 4.0414,
1041
+ "step": 144
1042
+ },
1043
+ {
1044
+ "epoch": 0.2760590195145169,
1045
+ "grad_norm": 8.904756546020508,
1046
+ "learning_rate": 1.3502555055861625e-05,
1047
+ "loss": 4.4121,
1048
+ "step": 145
1049
+ },
1050
+ {
1051
+ "epoch": 0.27796287482151355,
1052
+ "grad_norm": 10.7162504196167,
1053
+ "learning_rate": 1.3048827453426203e-05,
1054
+ "loss": 4.5674,
1055
+ "step": 146
1056
+ },
1057
+ {
1058
+ "epoch": 0.2798667301285102,
1059
+ "grad_norm": 10.042287826538086,
1060
+ "learning_rate": 1.2601101082383917e-05,
1061
+ "loss": 4.6137,
1062
+ "step": 147
1063
+ },
1064
+ {
1065
+ "epoch": 0.2817705854355069,
1066
+ "grad_norm": 9.6063871383667,
1067
+ "learning_rate": 1.2159498346654094e-05,
1068
+ "loss": 4.24,
1069
+ "step": 148
1070
+ },
1071
+ {
1072
+ "epoch": 0.2836744407425036,
1073
+ "grad_norm": 11.02759838104248,
1074
+ "learning_rate": 1.1724139976015306e-05,
1075
+ "loss": 4.5189,
1076
+ "step": 149
1077
+ },
1078
+ {
1079
+ "epoch": 0.28557829604950025,
1080
+ "grad_norm": 9.639123916625977,
1081
+ "learning_rate": 1.1295144993099068e-05,
1082
+ "loss": 4.4337,
1083
+ "step": 150
1084
+ },
1085
+ {
1086
+ "epoch": 0.28557829604950025,
1087
+ "eval_loss": 1.0172055959701538,
1088
+ "eval_runtime": 65.4679,
1089
+ "eval_samples_per_second": 13.518,
1090
+ "eval_steps_per_second": 3.391,
1091
+ "step": 150
1092
  }
1093
  ],
1094
  "logging_steps": 1,
 
1117
  "attributes": {}
1118
  }
1119
  },
1120
+ "total_flos": 2.146499429400576e+17,
1121
  "train_batch_size": 8,
1122
  "trial_name": null,
1123
  "trial_params": null